Keysight Technologies Inc. Advances 5G-Advanced Technology with AI-Powered Innovations

The demonstration showcased a mobile test platform powered by Qualcomm's 5G Modem-RF, integrated with Keysight’s robust network emulation solutions. In a controlled lab setting, the ML-based CSI feedback method achieved an impressive over 40 percent improvement in downlink throughput compared to the existing 3GPP eType II CSI reporting during four-layer (rank-4) operations. Visitors can experience this live demonstration at the Keysight booth (Hall 5, #5F41).

As 5G-Advanced networks increasingly utilize more antennas and wider channels, the importance of CSI in effective network operation grows. It plays a crucial role in steering beams and selecting the appropriate transmission settings. However, greater detail in CSI can lead to increased uplink reporting overhead, particularly in higher-layer MIMO systems, creating a challenge in balancing performance with signaling efficiency.

To tackle these challenges, Keysight and Qualcomm conducted tests under fixed CSI feedback constraints. The ML-based compression method proved to be a more efficient representation of channel conditions compared to the standardized eType II method. This allowed for the retention of essential information needed for precise beamforming and link decisions, ultimately supporting scalable advanced MIMO configurations. Moreover, this achievement contributes to ongoing industry efforts focused on exploring AI-native physical-layer enhancements that will be integral to future 6G wireless systems.

Tingfang Ji, Vice President of Engineering and Head of 6G Research at Qualcomm Technologies, emphasized the significance of efficient CSI feedback as antenna dimensions and spatial layers expand. "This demonstration shows how Qualcomm’s advanced machine learning algorithms can significantly improve downlink performance over conventional eType II CSI reporting, supporting continued 5G-Advanced innovation and laying the foundation for future AI-native 6G systems," Ji stated.

Lucas Hansen, Vice President and General Manager of the Wireless Test Group at Keysight, echoed this sentiment, highlighting the critical role of AI-native enhancements at the physical layer for scaling next-generation wireless networks. “By combining Qualcomm’s modem test platform with our AI-enabled base station emulation solutions, we are enabling rigorous evaluation of ML-based CSI compression and its impact on advanced MIMO performance and 6G research directions,” Hansen said.

The collaboration between Keysight and Qualcomm marks a significant step towards the future of telecommunications, emphasizing the role of AI in enhancing wireless performance. As the industry gears up for the transition to 6G, innovations like these will be essential for meeting the demands of increasingly complex and data-intensive networks.

With continued investment in research and development, Keysight Technologies remains committed to empowering innovators and facilitating the next wave of technological advancements across various sectors, including communications, industrial automation, and more.

For further information about this demonstration and other innovations, visit Keysight's booth at MWC or explore their offerings online.